湖南师范大学 物理与信息科学学院,湖南,长沙,410000
纸质出版:2016
移动端阅览
汪丹, 刘辉, 李可, 周威. 基于PCA-PSO的图像匹配和拼接[J]. 微电子学与计算机, 2016, 33(8): 117-120.
WANG Dan, LIU Hui, LI Ke, et al. Images Matching and Stitching Based on PCA-PSO[J]. 2016, 33(8): 117-120.
针对传统图像匹配算法和基于PCA的图像匹配算法误匹配较高进行改进.首先
利用SIFT生成128维描述子向量矩阵
PCA即主分量分析法对矩阵进行降维.然后
以一幅图的每个特征点描述子向量为基准
在另一幅图的特征点描述子矩阵中利用PSO即粒子群优化算法寻找基准图特征点的全局最优解即匹配对.最后利用这些匹配对进行图像拼接.与基于距离的传统匹配法相比
本算法匹配正确率更高
图像拼接质量更好.
Traditional images matching usually got some wrong matchers
which mean need to improve.First of all
get the 128-D descriptors according to SIFT
Make the dimensions less by using PCA and then find the best matchers by using PSO and finally start to stitch. Contrast to the traditional matching method and the images matching method based on PCA
the algorithm in this paper proved to be more accurate and it makes the following stitching better as well.
李俊杰. 一种基于K-D树结构和时空近似最优匹配的视频修复方法[D]. 长春: 吉林大学, 2011.
马杰. 360度全景图像拼接技术研究[D]. 成都: 西南财经大学, 2012.
Lowe DG. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. DOI: 91
C J Harris, M. StePhens. A combined corner and edge detector[C]//Proceedings of the 4th Alvey Vision Conference. [s. l. ]: IEEE, 1988: 147-150.
Kennedy J, Eberhart R, Particle swarm optimization[C]//Proc of the IEEE Int'l Conf. on Neural Networks. Piscataway: IEEE Service Center, 1995: 1942-1948.
Herbert Bay, Tinne Tuytelaars, Luc Van Gool. Speeded Up Robust Features[C]//Proceedings of the 9th Conference on Computer Vision. Berlin Heidelbery: springer, 2006: 404-417.
Peter N Belhumeur, Joao P Hespanha, David J Kriengman. Eigenfaces vs fisherfaces: recognition using class specific lin-earprojection[J]. IEEE Trans on Pattern Anal Machine Intell, 1997, 19(7): 711-720. DOI: 711
0
浏览量
11
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010602201714号